Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3287 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5450. Min Act: -0.0000

Data Index: 566770 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4763. Min Act: -0.0000

Data Index: 8656 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4265. Min Act: -0.0000

Data Index: 355770 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4777. Min Act: -0.0000

Data Index: 40147 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4328. Min Act: -0.0000

Data Index: 967591 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4472. Min Act: -0.0000

Data Index: 962892 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4472. Min Act: -0.0000

Data Index: 980623 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1206412 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5061. Min Act: -0.0000

Data Index: 470201 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4294. Min Act: -0.0000

Data Index: 625887 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4085. Min Act: -0.0000

Data Index: 888236 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4500. Min Act: -0.0000

Data Index: 699504 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1203789 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3616. Min Act: -0.0000

Data Index: 240980 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4525. Min Act: -0.0000

Data Index: 828820 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4146. Min Act: -0.0000

Data Index: 440263 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4099. Min Act: -0.0000

Data Index: 286970 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3575. Min Act: -0.0000

Data Index: 103835 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3352. Min Act: -0.0000

Data Index: 226201 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4321. Min Act: -0.0000

Data Index: 236727 (C4 (Web Text))

Max Activating Token Index: 819